INDEX

Explanations

mentions of geographical locations

oai_token-act-pair · gpt-3.5-turbo

the preposition "in."

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

NOW

-0.73

CLASSIFIED

-0.68

Features

-0.67

 cues

-0.66

ESA

-0.64

 hooks

-0.63

TIME

-0.63

 ingred

-0.63

ATURES

-0.62

 selves

-0.62

POSITIVE LOGITS

 conjunction

1.08

 lieu

1.05

clusions

1.04

 accordance

1.02

efficiency

1.00

 vain

0.99

effic

0.98

roads

0.95

patient

0.94

 relation

0.93

Activations Density 0.248%

mentions of geographical locations

the preposition "in."

No Comments

No Known Activations